{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CAZWEKCEA4IOX2ISS3YHXO6YPB","short_pith_number":"pith:CAZWEKCE","schema_version":"1.0","canonical_sha256":"10336228440710ebe91296f07bbbd878795e85d88adf5eceb6e86c93fb24dfcd","source":{"kind":"arxiv","id":"2501.18753","version":1},"attestation_state":"computed","paper":{"title":"INT: Instance-Specific Negative Mining for Task-Generic Promptable Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Hu, Shaogang Gong, Zixu Cheng","submitted_at":"2025-01-30T21:07:14Z","abstract_excerpt":"Task-generic promptable image segmentation aims to achieve segmentation of diverse samples under a single task description by utilizing only one task-generic prompt. Current methods leverage the generalization capabilities of Vision-Language Models (VLMs) to infer instance-specific prompts from these task-generic prompts in order to guide the segmentation process. However, when VLMs struggle to generalise to some image instances, predicting instance-specific prompts becomes poor. To solve this problem, we introduce \\textbf{I}nstance-specific \\textbf{N}egative Mining for \\textbf{T}ask-Generic P"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.18753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-30T21:07:14Z","cross_cats_sorted":[],"title_canon_sha256":"d4c53a43d19e55af6bacd19ccc101098cf929d83811ff085d4b69b03bc26304f","abstract_canon_sha256":"d2f2056b0c9a0c1b4082e54e1c93c64bd2bd339586577e0352bcea536f4d6e2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:51.022891Z","signature_b64":"u5kx0ABryGUXmggu+UZgaxljmcNYa9j2SSBfu+K6qrU8HmLBNn6vw9v203D2JSeZZMMSPDAjnQx/MEfzvG4HAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10336228440710ebe91296f07bbbd878795e85d88adf5eceb6e86c93fb24dfcd","last_reissued_at":"2026-07-05T10:07:51.022390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:51.022390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"INT: Instance-Specific Negative Mining for Task-Generic Promptable Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Hu, Shaogang Gong, Zixu Cheng","submitted_at":"2025-01-30T21:07:14Z","abstract_excerpt":"Task-generic promptable image segmentation aims to achieve segmentation of diverse samples under a single task description by utilizing only one task-generic prompt. Current methods leverage the generalization capabilities of Vision-Language Models (VLMs) to infer instance-specific prompts from these task-generic prompts in order to guide the segmentation process. However, when VLMs struggle to generalise to some image instances, predicting instance-specific prompts becomes poor. To solve this problem, we introduce \\textbf{I}nstance-specific \\textbf{N}egative Mining for \\textbf{T}ask-Generic P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18753","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.18753/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.18753","created_at":"2026-07-05T10:07:51.022449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18753v1","created_at":"2026-07-05T10:07:51.022449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18753","created_at":"2026-07-05T10:07:51.022449+00:00"},{"alias_kind":"pith_short_12","alias_value":"CAZWEKCEA4IO","created_at":"2026-07-05T10:07:51.022449+00:00"},{"alias_kind":"pith_short_16","alias_value":"CAZWEKCEA4IOX2IS","created_at":"2026-07-05T10:07:51.022449+00:00"},{"alias_kind":"pith_short_8","alias_value":"CAZWEKCE","created_at":"2026-07-05T10:07:51.022449+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.18050","citing_title":"ArgusCogito: Chain-of-Thought for Cross-Modal Synergy and Omnidirectional Reasoning in Camouflaged Object Segmentation","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CAZWEKCEA4IOX2ISS3YHXO6YPB","json":"https://pith.science/pith/CAZWEKCEA4IOX2ISS3YHXO6YPB.json","graph_json":"https://pith.science/api/pith-number/CAZWEKCEA4IOX2ISS3YHXO6YPB/graph.json","events_json":"https://pith.science/api/pith-number/CAZWEKCEA4IOX2ISS3YHXO6YPB/events.json","paper":"https://pith.science/paper/CAZWEKCE"},"agent_actions":{"view_html":"https://pith.science/pith/CAZWEKCEA4IOX2ISS3YHXO6YPB","download_json":"https://pith.science/pith/CAZWEKCEA4IOX2ISS3YHXO6YPB.json","view_paper":"https://pith.science/paper/CAZWEKCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18753&json=true","fetch_graph":"https://pith.science/api/pith-number/CAZWEKCEA4IOX2ISS3YHXO6YPB/graph.json","fetch_events":"https://pith.science/api/pith-number/CAZWEKCEA4IOX2ISS3YHXO6YPB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CAZWEKCEA4IOX2ISS3YHXO6YPB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CAZWEKCEA4IOX2ISS3YHXO6YPB/action/storage_attestation","attest_author":"https://pith.science/pith/CAZWEKCEA4IOX2ISS3YHXO6YPB/action/author_attestation","sign_citation":"https://pith.science/pith/CAZWEKCEA4IOX2ISS3YHXO6YPB/action/citation_signature","submit_replication":"https://pith.science/pith/CAZWEKCEA4IOX2ISS3YHXO6YPB/action/replication_record"}},"created_at":"2026-07-05T10:07:51.022449+00:00","updated_at":"2026-07-05T10:07:51.022449+00:00"}